Veo 3.1 Video Extend

Name: Veo 3.1 Video Extend
Author: Google

google/veo3.1/video-extend

Veo3.1 Extend Video is Google's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.

Use in agent Get API key

Base price: $2.80USD / run
Execution: async
Model type: video
Input fields: 8

Production route

Try the model

Playground

Open playground

Input

Prompt(string)

The text prompt describing how the video should be extended

Video(string)

Video to extend: MP4 at 24 fps, 720p (for example a Veo output). Veo appends the requested duration to it.

Duration(integer)

Length of the generated extension in seconds. Allowed values: 7.

Resolution(string)

Output resolution. Extensions are generated at 720p. Allowed values: 720p.

Aspect Ratio(string)

Output aspect ratio. `auto` follows the input. Allowed values: auto, 16:9, 9:16.

Generate Audio(boolean)

Generate synchronized audio. Videos without audio are cheaper.

Negative Prompt(string)

What to avoid in the video.

Seed(integer)

Random seed for more reproducible results. Range: 0 to 4294967295.

OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price: $2.80 / run
Billing formula: (params.duration ?? 7) * ((params.resolution ?? "720p") == "720p" ? ((params.generate_audio ?? true) ? 0.40 : 0.20) : (params.resolution ?? "720p") == "1080p" ? ((params.generate_audio ?? true) ? 0.40 : 0.20) : (params.resolution ?? "720p") == "4k" ? ((params.generate_audio ?? true) ? 0.60 : 0.40) : (0 / 0))

Context & modalities

Input: Schema-defined
Output: video

Capabilities

Chat: Not supported
Vision: Not supported
Reasoning: Not supported
Structured output: Not supported
Function calling: Not supported
Audio input: Not supported

Access

Provider: Google
Model ID: google/veo3.1/video-extend
Execution: async
API: Unified Run API
Endpoint: /v1/run

API README

Veo 3.1 Video Extend

google/veo3.1/video-extend continues existing footage beyond its ending while carrying forward motion, subjects, camera behavior, and scene context. Veo 3.1 improves instruction following, physical consistency, character continuity, and audiovisual quality while supporting more ways to anchor or continue a shot. This combination makes the model a practical choice when the creative outcome depends on those qualities rather than on a generic media conversion.

For production work with google/veo3.1/video-extend, the video continuation workflow suits storyboards, campaign films, product moments, narrative shots, and visual concepts that need coherent motion rather than isolated animated frames. The result is most reliable when the source material and creative brief clearly describe the intended subject, progression, visual or sonic character, and the qualities that must remain unchanged.

Highlights

Seam-aware continuation extends source footage while preserving movement and scene identity.

Improved physical coherence strengthens object interactions, character movement, and cause-and-effect across shots.

Visual continuity maintains subjects and scene logic across the generated sequence.

Native audio generation coordinates dialogue, ambience, and sound effects with the visual action.

Pricing

Official Google list price per generated second.

Resolution	Audio off	Audio on
720p	$0.20/s	$0.40/s

Default: 7 seconds at 720p with audio = $2.80.

Input requirements: the source video must be 24 fps 720p MP4 (Veo outputs qualify); other frame rates are rejected upstream with "Video fps mismatch" and are not billed. The returned video contains the source clip followed by the extension.

When to Use

✅ Good fit	❌ Consider alternatives
The model's named workflow matches the source material and intended output	A different input modality or model route is required
A managed asynchronous result is suitable for the production pipeline	A synchronous, interactive editor is essential
The documented controls cover the required duration, framing, or format	The project needs controls outside this endpoint's schema
Creative iteration benefits from a repeatable request structure	Exact deterministic pixels, frames, geometry, or samples are mandatory
A finished downloadable media asset is the desired deliverable	Editable source layers or a native project file are required

Prompt Guide

For generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.

{
  "prompt": "A paper boat drifting down a rain-soaked street at dusk, cinematic close-up, soft reflections",
  "video": "https://example.com/clip.mp4",
  "duration": 7,
  "resolution": "720p",
  "aspect_ratio": "auto",
  "generate_audio": true
}

Technical Specs

Spec	Value
Model ID	`google/veo3.1/video-extend`
Inputs	aspect_ratio, duration, generate_audio, negative_prompt, prompt, resolution, seed, video
Required inputs	prompt, video
Output fields	content_type, url
Execution	Async (submit, then poll for result)
Duration	7 seconds
Resolution	720p
Aspect Ratio	auto / 16:9 / 9:16

Related Models

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API

Unified Run API endpoint

https://api.sandbase.ai/v1/run

Model ID

google/veo3.1/video-extend

# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "google/veo3.1/video-extend",
  "prompt": "Continue the scene naturally, maintaining the same style and motion.",
  "duration": 7,
  "resolution": "720p",
  "aspect_ratio": "auto",
  "generate_audio": true
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All image & video models

Model	Type	Default price	Released
Veo 3.1 Video ExtendThis model `Google`	Video	$2.80 / run	Dec 15, 2025
Gemini Omni Flash 1.1 Edit `Google`	Video	$1.12 / run	Aug 27, 2026
Gemini Omni Flash 1.1 Text to Video `Google`	Video	$0.80 / run	Aug 27, 2026
Gemini Omni Flash 1.1 Image to Video `Google`	Video	$0.80 / run	Aug 27, 2026
Gemini Omni Flash 1.1 Reference to Video `Google`	Video	$0.80 / run	Aug 27, 2026
Gemini Omni Flash Reference to Video `Google`	Video	$1.04 / run	Jun 30, 2026

Questions

FAQ

How do I call Veo 3.1 Video Extend through SandBase?

Create a SandBase API key, then send requests with the model ID "google/veo3.1/video-extend" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

Do I need a separate Google account?

No. One SandBase API key and balance gives you access to Veo 3.1 Video Extend and the other models in the catalog; you do not need to sign up with Google separately.